Instructions to use novakat/nerkor-hubert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use novakat/nerkor-hubert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="novakat/nerkor-hubert")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("novakat/nerkor-hubert") model = AutoModelForTokenClassification.from_pretrained("novakat/nerkor-hubert") - Notebooks
- Google Colab
- Kaggle
Hungarian named entity recognition model with four entity types: PER ORG LOC MISC
- Pretrained model used: SZTAKI-HLT/hubert-base-cc
- Finetuned on NYTK-NerKor Corpus
Limitations
- max_seq_length = 448
See https://huggingface.co/novakat/nerkor-cars-onpp-hubert for a much more elaborate Hungarian named entity model.
- Downloads last month
- 9